DocumentCode :
2445297
Title :
Initialising the continuous Hopfield net
Author :
Lai, W.K. ; Coghill, G.G.
Author_Institution :
Dept. of Electr. & Electron. Eng., Auckland Univ., New Zealand
Volume :
7
fYear :
1994
fDate :
27 Jun-2 Jul 1994
Firstpage :
4640
Abstract :
In this paper, we compare some of the commonly used initialising schemes for the Hopfield neural net. This is demonstrated by solving an optimization problem which is representative of a class of problems that can be found in many application areas, such as engineering, medicine and finance. We also introduce a new initialising scheme which may not only be used for this particular application, but in other areas as well. Simulation results are provided to validate each approach
Keywords :
Hopfield neural nets; optimisation; search problems; continuous Hopfield neural net; heuristics; initialising schemes; optimization; search space; Cities and towns; Finance; Hopfield neural networks; Medical simulation; Neural networks; Neurofeedback; Neurons; Power engineering and energy; Scholarships; Traveling salesman problems;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
Type :
conf
DOI :
10.1109/ICNN.1994.375024
Filename :
375024
Link To Document :
بازگشت